AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification

Jun Hu, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He

AAAI 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use self-teaching Graph Transformer with cold-start mask instead of MLP-student distillationNTSFormer · Goodreads-NC (All test nodes)accuracy (%): 55.65 -> 61.58 (SGKD vs NTSFormer)Improved
add self-teaching instead of separate GLNN-style MLP student (ablation)NTSFormer · Movies, Ele-fashion, Goodreads-NCaccuracy (%)Improved
add multimodal graph pre-computation with separate text and visual tokens (ablation)NTSFormer · Movies, Ele-fashion, Goodreads-NCaccuracy (%)Improved
add MoE input projection instead of shared linear projection (ablation)NTSFormer · Movies, Ele-fashion, Goodreads-NCaccuracy (%)Improved
use fewer than 3 routed experts (ablation)NTSFormer MoE input projection · Movies, Ele-fashion, Goodreads-NCaccuracy (%)Hurt
use multiple Transformer layers instead of one (ablation)NTSFormer · Moviesaccuracy (%): 45.22 -> 46.12Improved
use multiple Transformer layers instead of one (ablation)NTSFormer · Ele-fashionaccuracy (%): 83.54 -> 83.37 (2 layers); 83.67 (4 layers)No clear effect
increase Transformer layers from 2 to 4 (ablation)NTSFormer · Moviesaccuracy (%): 46.12 -> 45.32No clear effect
use GNNs and multimodal GNNs under isolationGraphSAGE, MMGCN, MGAT, MIG · Movies, Ele-fashion, Goodreads-NCaccuracy (%): MLP 55.56 vs GraphSAGE 41.65 (Goodreads-NC All)Hurt
use Graph Transformers (Polynormer, SGFormer, NAGphormer) instead of MLPisolated cold-start inference · Goodreads-NC (All test nodes)accuracy (%): 55.56 -> 38.79 (Polynormer)Hurt
distill GNN teacher into MLP student (GLNN, SGKD, SimMLP)MLP · Movies (All test nodes)accuracy (%): 41.85 -> 43.45 (SimMLP)Improved
one-time pre-computation of graph structure for trainingNTSFormer · Goodreads-NCtraining time (s): 1437s (MUSE) -> 260sImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy